| 1 |
/* { dg-do compile } */ |
| 2 |
/* { dg-options "-mrvv-vector-bits=scalable -march=rv32gcv -mabi=ilp32 -fno-schedule-insns -fno-schedule-insns2" } */ |
| 3 |
|
| 4 |
#include "riscv_vector.h" |
| 5 |
|
| 6 |
void f5 (void * restrict in, void * restrict out, int l, int n, int m) |
| 7 |
{ |
| 8 |
for (int i = 0; i < l; i++){ |
| 9 |
for (int j = 0; j < m; j++){ |
| 10 |
for (int k = 0; k < n; k++) |
| 11 |
{ |
| 12 |
vfloat32mf2_t v = __riscv_vle32_v_f32mf2 (in + i + j, 17); |
| 13 |
__riscv_vse32_v_f32mf2 (out + i + j, v, 17); |
| 14 |
} |
| 15 |
} |
| 16 |
} |
| 17 |
} |
| 18 |
|
| 19 |
void f7 (void * restrict in, void * restrict out, int l, int n, int m) |
| 20 |
{ |
| 21 |
for (int i = 0; i < l; i++){ |
| 22 |
for (int j = 0; j < m; j++){ |
| 23 |
for (int k = 0; k < n; k++) |
| 24 |
{ |
| 25 |
vfloat32m1_t v = __riscv_vle32_v_f32m1 (in + i + j, 17); |
| 26 |
__riscv_vse32_v_f32m1 (out + i + j, v, 17); |
| 27 |
} |
| 28 |
} |
| 29 |
} |
| 30 |
} |
| 31 |
|
| 32 |
void f9 (void * restrict in, void * restrict out, int l, int n, int m) |
| 33 |
{ |
| 34 |
for (int i = 0; i < l; i++){ |
| 35 |
for (int j = 0; j < m; j++){ |
| 36 |
for (int k = 0; k < n; k++) |
| 37 |
{ |
| 38 |
vfloat32m2_t v = __riscv_vle32_v_f32m2 (in + i + j, 17); |
| 39 |
__riscv_vse32_v_f32m2 (out + i + j, v, 17); |
| 40 |
} |
| 41 |
} |
| 42 |
} |
| 43 |
} |
| 44 |
|
| 45 |
void f11 (void * restrict in, void * restrict out, int l, int n, int m) |
| 46 |
{ |
| 47 |
for (int i = 0; i < l; i++){ |
| 48 |
for (int j = 0; j < m; j++){ |
| 49 |
for (int k = 0; k < n; k++) |
| 50 |
{ |
| 51 |
vfloat32m4_t v = __riscv_vle32_v_f32m4 (in + i + j, 17); |
| 52 |
__riscv_vse32_v_f32m4 (out + i + j, v, 17); |
| 53 |
} |
| 54 |
} |
| 55 |
} |
| 56 |
} |
| 57 |
|
| 58 |
void f13 (void * restrict in, void * restrict out, int l, int n, int m) |
| 59 |
{ |
| 60 |
for (int i = 0; i < l; i++){ |
| 61 |
for (int j = 0; j < m; j++){ |
| 62 |
for (int k = 0; k < n; k++) |
| 63 |
{ |
| 64 |
vfloat32m8_t v = __riscv_vle32_v_f32m8 (in + i + j, 17); |
| 65 |
__riscv_vse32_v_f32m8 (out + i + j, v, 17); |
| 66 |
} |
| 67 |
} |
| 68 |
} |
| 69 |
} |
| 70 |
|
| 71 |
|
| 72 |
/* { dg-final { scan-assembler-times {\.L[0-9]+\:\s+vle32\.v\s+v[0-9]+,\s*0\s*\([a-x0-9]+\)} 5 { target { no-opts "-O0" no-opts "-g" no-opts "-funroll-loops" } } } } */ |
| 73 |
/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*17,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-g" no-opts "-funroll-loops" } } } } */ |
| 74 |
/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*17,\s*e32,\s*m1,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-g" no-opts "-funroll-loops" } } } } */ |
| 75 |
/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*17,\s*e32,\s*m2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-g" no-opts "-funroll-loops" } } } } */ |
| 76 |
/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*17,\s*e32,\s*m4,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-g" no-opts "-funroll-loops" } } } } */ |
| 77 |
/* { dg-final { scan-assembler-times {vsetivli\s+zero,\s*17,\s*e32,\s*m8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-g" no-opts "-funroll-loops" } } } } */ |